Collagen derived Gly-Pro-type DPP-IV inhibitory peptides: Structure-activity relationship, inhibition kinetics and inhibition mechanism

Our previous study has demonstrated that both the amino acid at N3 position and peptide length affected the DPP-IV inhibitory activity of Gly-Pro-type peptides. To further elucidate their molecular mechanism, a combined approach of QSAR modeling, enzymatic kinetics and molecular docking was used. Results showed that the QSAR models of Gly-Pro-type tripeptides and Gly-Pro-type peptides containing 3-12 residues were successfully constructed by 5z-scale descriptor with R2 of 0.830 and 0.797, respectively. The lower values of electrophilicity, polarity, and side-chain bulk of amino acid at N3 position caused higher DPP-IV inhibitory activity of Gly-Pro-type peptides. Moreover, an appropriate increase in the length of Gly-Pro-type peptides did not change their competitive inhibition mode, but decreased their inhibition constants (Ki values) and increased interactions with DPP-IV. More importantly, the interactions between the residues at C-terminal of Gly-Pro-type peptides containing 5 ∼ 6 residues with S2 extensive subsites (Ser209, Phe357, Arg358) of DPP-IV increased the interactions of Gly residue at N1 position with the S2 subsites (Glu205, Glu206, Asn710, Arg125, Tyr662) and decreased the acylation level of DPP-IV-peptide complex, and thereby increasing peptides' DPP-IV inhibitory activity.

Machine learning and traditional QSAR modeling methods: a case study of known PXR activators

Pregnane X receptor (PXR), extensively expressed in human tissues related to digestion and metabolism, is responsible for recognizing and detoxifying diverse xenobiotics encountered by humans. To comprehend the promiscuous nature of PXR and its ability to bind a variety of ligands, computational approaches, viz., quantitative structure-activity relationship (QSAR) models, aid in the rapid dereplication of potential toxicological agents and mitigate the number of animals used to establish a meaningful regulatory decision. Recent advancements in machine learning techniques accommodating larger datasets are expected to aid in developing effective predictive models for complex mixtures (viz., dietary supplements) before undertaking in-depth experiments. Five hundred structurally diverse PXR ligands were used to develop traditional two-dimensional (2D) QSAR, machine-learning-based 2D-QSAR, field-based three-dimensional (3D) QSAR, and machine-learning-based 3D-QSAR models to establish the utility of predictive machine learning methods. Additionally, the applicability domain of the agonists was established to ensure the generation of robust QSAR models. A prediction set of dietary PXR agonists was used to externally-validate generated QSAR models. QSAR data analysis revealed that machine-learning 3D-QSAR techniques were more accurate in predicting the activity of external terpenes with an external validation squared correlation coefficient (R2) of 0.70 versus an R2 of 0.52 in machine-learning 2D-QSAR. Additionally, a visual summary of the binding pocket of PXR was assembled from the field 3D-QSAR models. By developing multiple QSAR models in this study, a robust groundwork for assessing PXR agonism from various chemical backbones has been established in anticipation of the identification of potential causative agents in complex mixtures.

Physiological variables in machine learning QSARs allow for both cross-chemical and cross-species predictions

A major challenge in ecological risk assessment is estimating chemical-induced effects across taxa without species-specific testing. Where ecotoxicological data may be more challenging to gather, information on species physiology is more available for a broad range of taxa. Physiology is known to drive species sensitivity but understanding about the relative contribution of specific underlying processes is still elusive. Consequently, there remains a need to understand which physiological processes lead to differences in species sensitivity. The objective of our study was to utilize existing knowledge about organismal physiology to both understand and predict differences in species sensitivity. Machine learning models were trained to predict chemical- and species-specific endpoints as a function of both chemical fingerprints/descriptors and physiological properties represented by dynamic energy budget (DEB) parameters. We found that random forest models were able to predict chemical- and species-specific endpoints, and that DEB parameters were relatively important in the models, particularly for invertebrates. Our approach illuminates how physiological properties may drive species sensitivity, which will allow more realistic predictions of effects across species without the need for additional animal testing.

A local QSAR model based on the stability of nitrenium ions to support the ICH M7 expert review on the mutagenicity of primary aromatic amines

BACKGROUND

Aromatic amines, often used as intermediates for pharmaceutical synthesis, may be mutagenic and therefore pose a challenge as metabolites or impurities in drug development. However, predicting the mutagenicity of aromatic amines using commercially available, quantitative structure-activity relationship (QSAR) tools is difficult and often requires expert review. In this study, we developed a shareable QSAR tool based on nitrenium ion stability.

RESULTS

The evaluation using in-house aromatic amine intermediates revealed that our model has prediction accuracy of aromatic amine mutagenicity comparable to that of commercial QSAR tools. The effect of changing the number and position of substituents on the mutagenicity of aromatic amines was successfully explained by the change in the nitrenium ion stability. Furthermore, case studies showed that our QSAR tool can support the expert review with quantitative indicators.

CONCLUSIONS

This local QSAR tool will be useful as a quantitative support tool to explain the substituent effects on the mutagenicity of primary aromatic amines. By further refinement through method sharing and standardization, our tool can support the International Council for Harmonisation of Technical Requirements for Pharmaceuticals for Human Use (ICH) M7 expert review with quantitative indicators.

Machine Learning Applied to the Modeling of Pharmacological and ADMET Endpoints

The well-known concept of quantitative structure-activity relationships (QSAR) has been gaining significant interest in the recent years. Data, descriptors, and algorithms are the main pillars to build useful models that support more efficient drug discovery processes with in silico methods. Significant advances in all three areas are the reason for the regained interest in these models. In this book chapter we review various machine learning (ML) approaches that make use of measured in vitro/in vivo data of many compounds. We put these in context with other digital drug discovery methods and present some application examples.

Building 2D classification models and 3D CoMSIA models on small-molecule inhibitors of both wild-type and T790M/L858R double-mutant EGFR

Epidermal growth factor receptor (EGFR) has received widespread attention because it is an important target for anticancer drug design. Mutations in the EGFR, especially the T790M/L858R double mutation, have made cancer treatment more difficult. We herein built the structure-activity relationship models of small-molecule inhibitors on wild-type and T790M/L858R double-mutant EGFR with a whole dataset of 379 compounds. For 2D classification models, we used ECFP4 fingerprints to build support vector machine and random forest models and used SMILES to build self-attention recurrent neural network models. Each of all six models resulted in an accuracy of above 0.87 and the Matthews correlation coefficient value of above 0.76 on the test set, respectively. We concluded that inhibitors containing anilinoquinoline and methoxy or fluoro phenyl are highly active against wild EGFR. Substructures such as anilinopyrimidine, acrylamide, amino phenyl, methoxy phenyl, and thienopyrimidinyl amide appeared more in highly active inhibitors against double-mutant EGFR. We also used self-organizing map to cluster the inhibitors into six subsets based on ECFP4 fingerprints and analyzed the activity characteristics of different scaffolds in each subset. Among them, three datasets, which are based on pteridin, anilinopyrimidine, and anilinoquinoline scaffold, were selected to build 3D comparative molecular similarity analysis models individually. Models with the leave-one-out coefficient of determination (q²) above 0.65 were selected, and five descriptor types (steric, electrostatic, hydrophobic, donor, and acceptor) were used to study the effects of side chains of inhibitors on the activity against wild-type and mutant-type EGFR.

Development of a new quantitative structure-activity relationship model for predicting Ames mutagenicity of food flavor chemicals using StarDrop™ auto-Modeller™

BACKGROUND

Food flavors are relatively low molecular weight chemicals with unique odor-related functional groups that may also be associated with mutagenicity. These chemicals are often difficult to test for mutagenicity by the Ames test because of their low production and peculiar odor. Therefore, application of the quantitative structure-activity relationship (QSAR) approach is being considered. We used the StarDrop™ Auto-Modeller™ to develop a new QSAR model.

RESULTS

In the first step, we developed a new robust Ames database of 406 food flavor chemicals consisting of existing Ames flavor chemical data and newly acquired Ames test data. Ames results for some existing flavor chemicals have been revised by expert reviews. We also collected 428 Ames test datasets for industrial chemicals from other databases that are structurally similar to flavor chemicals. A total of 834 chemicals' Ames test datasets were used to develop the new QSAR models. We repeated the development and verification of prototypes by selecting appropriate modeling methods and descriptors and developed a local QSAR model. A new QSAR model "StarDrop NIHS 834_67" showed excellent performance (sensitivity: 79.5%, specificity: 96.4%, accuracy: 94.6%) for predicting Ames mutagenicity of 406 food flavors and was better than other commercial QSAR tools.

CONCLUSIONS

A local QSAR model, StarDrop NIHS 834_67, was customized to predict the Ames mutagenicity of food flavor chemicals and other low molecular weight chemicals. The model can be used to assess the mutagenicity of food flavors without actual testing.

A novel artificial intelligence protocol to investigate potential leads for diabetes mellitus

Dipeptidyl peptidase-4 (DPP4) is highly participated in regulating diabetes mellitus (DM), and inhibitors of DPP4 may act as potential DM drugs. Therefore, we performed a novel artificial intelligence (AI) protocol to screen and validate the potential inhibitors from Traditional Chinese Medicine Database. The potent top 10 compounds were selected as candidates by Dock Score. In order to further screen the candidates, we used numbers of machine learning regression models containing support vector machines, bagging, random forest and other regression algorithms, as well as deep neural network models to predict the activity of the candidates. In addition, as a traditional method, 2D QSAR (multiple linear regression) and 3D QSAR methods are also applied. The AI methods got a better performance than the traditional 2D QSAR method. Moreover, we also built a framework composed of deep neural networks and transformer to predict the binding affinity of candidates and DPP4. Artificial intelligence methods and QSAR models illustrated the compound, 2007_4105, was a potent inhibitor. The 2007_4105 compound was finally validated by molecular dynamics simulations. Combining all the models and algorithms constructed and the results, Hypecoum leptocarpum might be a potential and effective medicine herb for the treatment of DM.

Polarizability: a promising descriptor to study chemical-biological interactions

Recently, we have defined atomic polarizability, a Conceptual Density Functional Theory (CDFT)-based reactivity descriptor, through an empirical method. Though the method is empirical, it is competent enough to meet the criteria of periodic descriptors and exhibit relativistic effect. Since the atomic data are very accurate, we have applied them to determine molecular polarizability. Molecular polarizability is an electronic parameter and has an impact on chemical-biological interactions. Thus, it plays a pivotal role in explaining such interactions through Structure Activity Relationships (SAR). In the present work, we have explored the application of polarizability in the real field through investigation of chemical-biological interactions in terms of molecular polarizability. A Quantitative Structure-Activity Relationship (QSAR) model is constructed to account for electronic effects owing to polarizability in ligand-substrate interactions. The study involves the prediction of various biological activities in terms of minimum block concentration, relative biological response, inhibitory growth concentration or binding affinity. Superior results are presented for the predicted and observed activities which support the accuracy of the proposed polarizability-QSAR model. Further, the results are considered from a biological viewpoint in order to understand the mechanism of interactions. The study is performed to explore the efficacy of the computational model based on newly proposed polarizability and not to establish the finest QSAR. For future studies, it is suggested that the descriptor polarizability should be contrasted with the use of other drug-like descriptors.

A model of atomic compressibility and its application in QSAR domain for toxicological property prediction

A model for computing the atomic compressibility (β) based on two periodic descriptors, namely, absolute radius (r) and atomic electrophilicity index (ω), is proposed as[Formula: see text]The ansatz is invoked to compute compressibilities of atoms of 57 elements of the periodic table. The computed atomic data exhibits all sine qua non of periodic properties. Further, the concept group compressibility (Gβ) is also established invoking additivity property using some molecules with different functional groups and consequently utilized in correlating with molecular polarizability. Since toxicity prediction is an imperative need of the hour, chemical reactivity descriptors are of paramount importance in the study of toxicological behaviour along with a lot of other molecular reactivity studies within a Quantitative Structure-Activity Relationship (QSAR) context. Hence, this quantity is applied in the modelling of toxicological property through QSAR and a comprehensive study is performed in an effort to investigate and validate the application of compressibility in determining its toxicological power. Consequently, varied 209 organic molecules are selected for studying the toxic effect on Tetrahymena pyriformis. A QSAR model is constructed in terms of compressibility which offers a superior prediction of toxicity independently without adopting additional descriptors or properties as in some other QSAR studies. Graphical abstract.

Quantitative structure-activity relationship for the partition coefficient of hydrophobic compounds between silicone oil and air

The silicon oil-air partition coefficients (K_SiO/A) of hydrophobic compounds are vital parameters for applying silicone oil as non-aqueous-phase liquid in partitioning bioreactors. Due to the limited number of K_SiO/A values determined by experiment for hydrophobic compounds, there is an urgent need to model the K_SiO/A values for unknown chemicals. In the present study, we developed a universal quantitative structure-activity relationship (QSAR) model using a sequential approach with macro-constitutional and micromolecular descriptors for silicone oil-air partition coefficients (K_SiO/A) of hydrophobic compounds with large structural variance. The geometry optimization and vibrational frequencies of each chemical were calculated using the hybrid density functional theory at the B3LYP/6-311G** level. Several quantum chemical parameters that reflect various intermolecular interactions as well as hydrophobicity were selected to develop QSAR model. The result indicates that a regression model derived from logK_SiO/A, the number of non-hydrogen atoms (#nonHatoms) and energy gap of E_LUMO and E_HOMO (E_LUMO-E_HOMO) could explain the partitioning mechanism of hydrophobic compounds between silicone oil and air. The correlation coefficient R² of the model is 0.922, and the internal and external validation coefficient, Q²_LOO and Q²_ext , are 0.91 and 0.89 respectively, implying that the model has satisfactory goodness-of-fit, robustness, and predictive ability and thus provides a robust predictive tool to estimate the logK_SiO/A values for chemicals in application domain. The applicability domain of the model was visualized by the Williams plot.

An automated framework for QSAR model building

Background

In-silico quantitative structure–activity relationship (QSAR) models based tools are widely used to screen huge databases of compounds in order to determine the biological properties of chemical molecules based on their chemical structure. With the passage of time, the exponentially growing amount of synthesized and known chemicals data demands computationally efficient automated QSAR modeling tools, available to researchers that may lack extensive knowledge of machine learning modeling. Thus, a fully automated and advanced modeling platform can be an important addition to the QSAR community.

Results

In the presented workflow the process from data preparation to model building and validation has been completely automated. The most critical modeling tasks (data curation, data set characteristics evaluation, variable selection and validation) that largely influence the performance of QSAR models were focused. It is also included the ability to quickly evaluate the feasibility of a given data set to be modeled. The developed framework is tested on data sets of thirty different problems. The best-optimized feature selection methodology in the developed workflow is able to remove 62–99% of all redundant data. On average, about 19% of the prediction error was reduced by using feature selection producing an increase of 49% in the percentage of variance explained (PVE) compared to models without feature selection. Selecting only the models with a modelability score above 0.6, average PVE scores were 0.71. A strong correlation was verified between the modelability scores and the PVE of the models produced with variable selection.

Conclusions

We developed an extendable and highly customizable fully automated QSAR modeling framework. This designed workflow does not require any advanced parameterization nor depends on users decisions or expertise in machine learning/programming. With just a given target or problem, the workflow follows an unbiased standard protocol to develop reliable QSAR models by directly accessing online manually curated databases or by using private data sets. The other distinctive features of the workflow include prior estimation of data modelability to avoid time-consuming modeling trials for non modelable data sets, an efficient variable selection procedure and the facility of output availability at each modeling task for the diverse application and reproduction of historical predictions. The results reached on a selection of thirty QSAR problems suggest that the approach is capable of building reliable models even for challenging problems.

Electronic supplementary material

The online version of this article (10.1186/s13321-017-0256-5) contains supplementary material, which is available to authorized users.

Network pharmacology-based approach of novel traditional Chinese medicine formula for treatment of acute skin inflammation in silico

Matrix metalloproteinase-9 (MMP-9) appears to play an important role in acute skin inflammation. Subantimicrobial dose of tetracycline has been demonstrated to inhibit the activity of MMP-9 protein. However, long-term use tetracycline will induce side effect. The catalytic site of MMP-9 is located at zinc-binding amino acids, His401, His405 and His411. We attempted to search novel medicine formula as MMP-9 inhibitors from traditional Chinese medicine (TCM) database by using in silico studies. We utilized high-throughput virtual screening to find which natural compounds could bind to the zinc-binding site. The quantitative structure-activity relationship (QSAR) models, which constructed by scaffold of MMP-9 inhibitors and its activities, were employed to predict the bio-activity of the natural compounds for MMP-9. The results showed that Celacinnine, Lobelanidine and Celallocinnine were qualified to interact with zinc-binding site and displayed well predictive activity. We found that celallocinnine was the best TCM compound for zinc binging sites of MMP-9 because the stable interactions were observed under dynamic condition. In addition, Celacinnine and Lobelanidine could interact with MMP-9 related protein that identified by drug-target interaction network analysis. Thus, we suggested the herbs Hypericum patulum, Sedum acre, and Tripterygium wilfordii that containing Celallocinnine, Celacinnine and Lobelanidine might be a novel medicine formula to avoid the side effect of tetracycline and increase the efficacy of treatment.

Investigation and prediction of protein precipitation by polyethylene glycol using quantitative structure-activity relationship models

Precipitation of proteins is considered to be an effective purification method for proteins and has proven its potential to replace costly chromatography processes. Besides salts and polyelectrolytes, polymers, such as polyethylene glycol (PEG), are commonly used for precipitation applications under mild conditions. Process development, however, for protein precipitation steps still is based mainly on heuristic approaches and high-throughput experimentation due to a lack of understanding of the underlying mechanisms. In this work we apply quantitative structure-activity relationships (QSARs) to model two parameters, the discontinuity point m* and the β-value, that describe the complete precipitation curve of a protein under defined conditions. The generated QSAR models are sensitive to the protein type, pH, and ionic strength. It was found that the discontinuity point m* is mainly dependent on protein molecular structure properties and electrostatic surface properties, whereas the β-value is influenced by the variance in electrostatics and hydrophobicity on the protein surface. The models for m* and the β-value exhibit a good correlation between observed and predicted data with a coefficient of determination of R²≥0.90 and, hence, are able to accurately predict precipitation curves for proteins. The predictive capabilities were demonstrated for a set of combinations of protein type, pH, and ionic strength not included in the generation of the models and good agreement between predicted and experimental data was achieved.

Molecular topology: a strategy to identify novel compounds against ulcerative colitis

In the present paper, a strategy to identify novel compounds against ulcerative colitis (UC) by molecular topology (MT) is presented. Several quantitative structure-activity relationship (QSAR) models based on molecular topology have been developed to predict inducible nitric oxide synthase (iNOS) and tumor necrosis factor alpha ([Formula: see text]) mediated anti-ulcerative colitis (UC) activity and protective activity against a dextran sulfate sodium (DSS)-induced UC model. Each one has been used for the screening of four previously selected compounds as potential therapeutic agents for UC: alizarin-3-methyliminodiacetic acid (AMA), Calcein, (+)-dibenzyl-L-tartrate, and Ro 41-0960. These four compounds were then tested in vitro and in vivo and confirmed AMA and Ro 41-0960 as the best lead candidates for further development against UC.

In silico model for predicting soil organic carbon normalized sorption coefficient (K(OC)) of organic chemicals

As a kind of in silico method, the methodology of quantitative structure-activity relationship (QSAR) has been shown to be an efficient way to predict soil organic carbon normalized sorption coefficients (KOC) values. In the present study, a total of 824 logKOC values were used to develop and validate a QSAR model for predicting KOC values. The model statistics parameters, adjusted determination coefficient (R(2)adj) of 0.854, the root mean square error (RMSE) of 0.472, the leave-one-out cross-validation squared correlation coefficient (Q(2)LOO) of 0.850, the external validation coefficient Q(2)ext of 0.761 and the RMSEext of 0.558 were obtained, which indicate satisfactory goodness of fit, robustness and predictive ability. The squared Moriguchi octanol-water partition coefficient (MLOGP2) explained 66.5% of the logKOC variance. The applicability domain of the current model has been extended to emerging pollutants like polybrominated diphenyl ethers, perfluorochemicals and heterocyclic toxins. The developed model can be used to predict the compounds with various functional groups including C=C, -C≡C-, -OH, -O-, -CHO, C=O, -C=O(O), -COOH, -C6H5, -NO2, -NH2, -NH-, N-, -N-N-, -NH-C(O)-NH-, -O-C(O)-NH2, -C(O)-NH2, -X(F, Cl, Br, I), -S-, -SH, -S(O)2-, -OS(O)2-, -NH-S(O)2-, (SR)2PH(OR)2 and Si.

Measurement of partition coefficients for selected polycyclic aromatic hydrocarbons between isolated plant cuticles and water

Partition coefficients between plant cuticles and water (Kcutw) were measured for 10 selected polycyclic aromatic hydrocarbons (PAHs) to evaluate the sorption capacity of plant cuticular layers for hydrophobic organic chemicals. The partitioning properties of PAHs between cuticles and water were evaluated by using (1) isolated cuticular layers and (2) leaf homogenate. The abaxial and adaxial cuticular layers of Euonymus japonicus were isolated by enzymatic digestion. A third-phase partitioning method using poly(dimethylsiloxane) (PDMS) was used to obtain Kcutw. The Kcutw values for the selected PAHs showed no significant differences between the abaxial and adaxial cuticular layers and ranged between 10(4.1) and 10(7.6). These values are close to or slightly higher than their 1-octanol/water partition coefficient (log Kow), indicating high sorption capacity of plant cuticles. On the contrary, partition coefficients between the lipid tissues of homogenized leaves and water were lower than those obtained using isolated cuticular layers by factors of 3.7-190, which is likely due to the breakdown of lipid layers. This indicates that the sorption of hydrophobic organic chemicals by plant leaves is better evaluated using isolated cuticles and that the sorption potential of plant leaves may be underestimated when leaf homogenates are used.

Predicting reductive debromination of polybrominated diphenyl ethers by nanoscale zerovalent iron and its implications for environmental risk assessment

The reductive debromination of polybrominated diphenyl ethers (PBDEs) by nanoscale zerovalent iron (nZVI) has proven to be a successful remediation approach. This study simulates the congener profiles and overall ecotoxicological impact of PBDE debromination by nZVI. The relationship between the calculated redox potential values and PBDE debromination rates was sufficiently strong to generate a satisfactory predictive capacity, which was further used to develop a quantitative structure-activity relationship (QSAR) model for the determination of the PBDE debromination patterns and dominant pathways. The predicted results of deca-BDE debromination showed that it would completely disappear within 30 days, but its lower brominated products, particularly tri- to penta-homologues, could exist in the environment even after 5 years. Formation and accumulation of more toxic, low brominated congeners through deca-BDE debromination suggest that deca-BDE may pose prolonged environmental risks. Changes in the toxic equivalent (TEQ) values during deca-BDE debromination parallel the occurrence and transformation of specific low brominated congeners with dioxin-like potency.